Data Reduction Physicist

Lead the design of next-generation data tiers for the CMS High-Level Trigger to enable high-throughput event processing and data reduction. Develop accelerator-native data formats optimized for GPU processing and build frameworks to quantify compression impacts and benchmark performance.

Responsibilities

• Design next-generation data structures that push the limits of data reduction to save 750 kHz while preserving physics performance and analysis flexibility.
• Ensure all formats are accelerator-native (e.g., structure-of-arrays, SoA) and optimised for high-throughput GPU processing.
• Build an end-to-end framework to rigorously quantify the impact of lossy compression, with clear metrics, reference analyses, and automated regression tests.
• Benchmark compression/decompression under realistic workloads: CPU/GPU cost, I/O throughput, memory footprint, and latency.
• Advance lossless compression, leveraging R³-reconstructed objects and pioneering AI/ML techniques.

Requirements

• Master’s degree with 2 to 6 years of professional experience since graduation or a PhD with a maximum of 3 years of professional experience since graduation.
• You have never had a CERN fellow or graduate contract before.
• Demonstrated contributions to trigger and/or reconstruction in HEP (or comparable high-throughput scientific software).
• Practical understanding of end-to-end HEP experiment operations, from detector readout to reconstruction, calibrations, datasets, and final physics results.
• Experience working in a large international collaboration (code review, CI/CD, documentation) is a plus.
• Knowledge with LHC experiments and their data formats is a plus.
• Expertise in data compression techniques is a plus (lossless and/or lossy).
• Experience applying AI/ML methods (e.g., autoencoders) to data reduction is a plus.
• Proficiency in GPU programming and heterogeneous computing is a plus.
• Your studies focused on Physics.
• High proficiency in C++, Python, and ROOT.
• Solid understanding of event reconstruction, including calibrations and commonly used data formats in HEP.
• Spoken and written English, with a commitment to learn French.

Skills

• Trigger and reconstruction in HEP
• High-throughput scientific software
• HEP experiment operations
• Detector Readout
• Event Reconstruction
• Data calibrations
• HEP data formats
• C/C++ Programming
• Python Programming
• ROOT software
• Data compression techniques
• AI/ML for data reduction
• GPU Programming
• Heterogeneous computing
• Code Reviews
• Continuous Integration
• Documentation
• Physics domain knowledge

Languages

English, French